CN112800995A - Intelligent particle size detection method using multi-scale feature weighting - Google Patents
Intelligent particle size detection method using multi-scale feature weighting Download PDFInfo
- Publication number
- CN112800995A CN112800995A CN202110155232.4A CN202110155232A CN112800995A CN 112800995 A CN112800995 A CN 112800995A CN 202110155232 A CN202110155232 A CN 202110155232A CN 112800995 A CN112800995 A CN 112800995A
- Authority
- CN
- China
- Prior art keywords
- feature map
- distance
- scale
- image
- feature
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
- G06F18/253—Fusion techniques of extracted features
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Biophysics (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Molecular Biology (AREA)
- General Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- Biomedical Technology (AREA)
- Health & Medical Sciences (AREA)
- Multimedia (AREA)
- Image Analysis (AREA)
Abstract
The application relates to intelligent particle size detection in the field of intelligent energy, and particularly discloses an intelligent particle size detection method using multi-scale feature weighting. The detection method extracts high-dimensional features in a pulverized coal image through machine vision based on deep learning and classifies based on the extracted features to detect whether large-particle pulverized coal exceeding a predetermined size exists in pulverized coal to be fed into a combustion chamber, so as to ensure combustion efficiency. In particular, in the classification process, the detection method does not need to actually detect the object exceeding the preset size from the feature map, so that the detection precision can be improved by directly converting the overall scale of the feature map so as to obtain a fusion feature map sensitive to the scale and further obtaining a classifier sensitive to the scale through information of different scales.
Description
Technical Field
The present invention relates to smart particle size detection in the field of smart energy, and more particularly, to a smart particle size detection method using multi-scale feature weighting, a smart particle size detection system using multi-scale feature weighting, and an electronic device.
Background
The current power generation equipment mainly comprises a power station boiler, a steam turbine, a gas turbine, a generator, a starter, a transformer and the like. Among the types of utility boilers, the pulverized coal furnace is a main type that blows pulverized coal pulverized into fine particles to a combustion chamber during operation so that the pulverized coal is burned out in the air. Therefore, the diameter of the pulverized coal particles needs to be sized to be sufficiently in contact with oxygen in a short time, however, in actual use, large-sized pulverized coal still enters the combustion chamber, which affects the combustion rate of the pulverized coal.
Therefore, an intelligent detection method for the size of the pulverized coal particles to be introduced into the combustion chamber is desired.
At present, deep learning and neural networks have been widely applied in the fields of computer vision, natural language processing, text signal processing, and the like. In addition, deep learning and neural networks also exhibit a level close to or even exceeding that of humans in the fields of image classification, object detection, semantic segmentation, text translation, and the like.
Deep learning and development of a neural network provide a new solution idea and scheme for intelligent detection of the size of the coal dust particles.
Disclosure of Invention
The present application is proposed to solve the above-mentioned technical problems. Embodiments of the present application provide an intelligent particle size detection method using multi-scale feature weighting, an intelligent particle size detection system using multi-scale feature weighting, and an electronic device, which detect whether large-particle pulverized coal exceeding a predetermined size exists in pulverized coal to be introduced into a combustion chamber by extracting high-dimensional features in a pulverized coal image through machine vision based on deep learning and classifying based on the extracted features, so as to ensure combustion efficiency. In particular, in the classification process, the detection method does not need to actually detect the object exceeding the preset size from the feature map, so that the detection precision can be improved by directly converting the overall scale of the feature map so as to obtain a fusion feature map sensitive to the scale and further obtaining a classifier sensitive to the scale through information of different scales.
According to one aspect of the present application, there is provided a smart particle size detection method using multi-scale feature weighting, comprising:
acquiring an image to be detected, wherein the image to be detected is a pulverized coal image entering a combustion chamber;
the image to be detected passes through a first convolutional neural network to extract a first characteristic diagram corresponding to the image to be detected;
downsampling the first feature map to obtain a first downsampled feature map, and passing the first downsampled feature map through a second convolutional neural network to obtain a second feature map;
downsampling the second feature map to obtain a second downsampled feature map, and passing the second downsampled feature map through a third convolutional neural network to obtain a third feature map;
inputting the obtained reference image into the first convolution neural network to extract a reference characteristic diagram corresponding to the reference image, wherein the reference image is a coal powder image marked with large-particle coal powder with a size exceeding a preset size;
respectively calculating a first distance, a second distance and a third distance between the reference feature map and the first feature map, the second feature map and the third feature map;
calculating a first weight, a second weight, and a third weight respectively corresponding to the first distance, the second distance, and the third distance with a prior probability calculation formula as follows: p ═ 2 x exp (-D) ]/[1+ exp (-D) ], where p denotes the prior probability and D denotes the distance;
fusing the first feature map, the second feature map and the third feature map by the first weight, the second weight and the third weight to obtain a fused feature map; and
and passing the fusion characteristic diagram through a classifier to obtain a classification result, wherein the classification result is used for indicating whether large-particle coal dust with a size exceeding a preset size exists in the coal dust to enter a combustion chamber in the image to be detected.
In the above method for detecting a size of a smart particle using multi-scale feature weighting, the second convolutional neural network has a preset depth, and the preset depth is greater than or equal to 5 and less than or equal to 10.
In the above method for detecting a size of a smart particle using multi-scale feature weighting, calculating a first distance, a second distance, and a third distance between the reference feature map and the first feature map, the second feature map, and the third feature map, respectively, includes: and respectively calculating cosine distances among the reference feature map, the first feature map, the second feature map and the third feature map to obtain the first distance, the second distance and the third distance.
In the above method for detecting a size of a smart particle using multi-scale feature weighting, calculating a first distance, a second distance, and a third distance between the reference feature map and the first feature map, the second feature map, and the third feature map, respectively, includes: and respectively calculating the mean square deviations between the reference feature map and the first feature map, the second feature map and the third feature map to obtain the first distance, the second distance and the third distance.
In the above method for detecting a size of a smart particle using multi-scale feature weighting, calculating a first distance, a second distance, and a third distance between the reference feature map and the first feature map, the second feature map, and the third feature map, respectively, includes: unifying a scale between the reference feature map and the first feature map; unifying the scale between the reference feature map and the second feature map; and unifying the scale between the reference feature map and the third feature map.
In the above method for detecting a size of an intelligent particle using multi-scale feature weighting, passing the fused feature map through a classifier to obtain a classification result, the method includes: passing the fused feature map through one or more fully connected layers to obtain a classified feature vector; and inputting the classification feature vector into a Softmax classification function to obtain the classification result.
In the above method for detecting a size of a smart particle using multi-scale feature weighting, the first convolutional neural network, the second convolutional neural network, and the third convolutional neural network are depth residual error networks.
According to another aspect of the present application, there is provided a smart particle size detection system using multi-scale feature weighting, comprising:
the device comprises an image acquisition unit to be detected, a data acquisition unit and a data processing unit, wherein the image acquisition unit to be detected is used for acquiring an image to be detected, and the image to be detected is a pulverized coal image entering a combustion chamber;
the first characteristic diagram generating unit is used for enabling the image to be detected obtained by the image to be detected obtaining unit to pass through a first convolutional neural network so as to extract a first characteristic diagram corresponding to the image to be detected;
a second feature map generation unit, configured to down-sample the first feature map obtained by the first feature map generation unit to obtain a first down-sampled feature map, and pass the first down-sampled feature map through a second convolutional neural network to obtain a second feature map;
a third feature map generation unit configured to down-sample the second feature map obtained by the second feature map generation unit to obtain a second down-sampled feature map, and pass the second down-sampled feature map through a third convolutional neural network to obtain a third feature map;
a reference feature map generating unit, configured to input the obtained reference image into the first convolutional neural network to extract a reference feature map corresponding to the reference image, where the reference image is a pulverized coal image marked with large-particle pulverized coal exceeding a predetermined size;
a distance calculating unit configured to calculate a first distance, a second distance, and a third distance between the reference feature map obtained by the reference feature map generating unit and the first feature map obtained by the first feature map generating unit, the second feature map obtained by the second feature map generating unit, and the third feature map obtained by the third feature map generating unit, respectively;
a weight calculation unit configured to calculate a first weight, a second weight, and a third weight respectively corresponding to the first distance, the second distance, and the third distance obtained by the distance calculation unit, using a prior probability calculation formula as follows: p ═ 2 x exp (-D) ]/[1+ exp (-D) ], where p denotes the prior probability and D denotes the distance;
a fused feature map generating unit configured to fuse the first feature map obtained by the first feature map generating unit, the second feature map obtained by the second feature map generating unit, and the third feature map obtained by the third feature map generating unit with the first weight, the second weight, and the third weight obtained by the weight calculating unit to obtain a fused feature map; and
and the classification result generating unit is used for enabling the fusion characteristic diagram obtained by the fusion characteristic diagram generating unit to pass through a classifier so as to obtain a classification result, and the classification result is used for indicating whether large-particle coal dust with the size exceeding the preset size exists in the coal dust to enter the combustion chamber in the image to be detected.
In the above intelligent particle size detection system using multi-scale feature weighting, the second convolutional neural network has a preset depth, and the preset depth is greater than or equal to 5 and less than or equal to 10.
In the above intelligent particle size detection system using multi-scale feature weighting, the distance calculation unit is further configured to: and respectively calculating cosine distances among the reference feature map, the first feature map, the second feature map and the third feature map to obtain the first distance, the second distance and the third distance.
In the above intelligent particle size detection system using multi-scale feature weighting, the distance calculation unit is further configured to: and respectively calculating the mean square deviations between the reference feature map and the first feature map, the second feature map and the third feature map to obtain the first distance, the second distance and the third distance.
In the above-mentioned intelligent particle size detection system using multi-scale feature weighting, the distance calculation unit includes: a first scale unifying subunit configured to unify a scale between the reference feature map and the first feature map; a second scale unifying subunit, configured to unify a scale between the reference feature map and the second feature map; and a third scale unifying subunit, configured to unify the scale between the reference feature map and the third feature map.
In the above-mentioned intelligent particle size detection system using multi-scale feature weighting, the classification result generating unit includes: the classification feature vector generation subunit is used for enabling the fusion feature map to pass through one or more full-connection layers so as to obtain a classification feature vector; and the classification subunit is used for inputting the classification feature vector obtained by the classification feature vector generation subunit into a Softmax classification function so as to obtain the classification result.
In the above-mentioned smart particle size detection system using multi-scale feature weighting, the first convolutional neural network, the second convolutional neural network, and the third convolutional neural network are depth residual error networks.
According to still another aspect of the present application, there is provided an electronic apparatus including: a processor; and a memory having stored therein computer program instructions which, when executed by the processor, cause the processor to perform the intelligent particle size detection method using multi-scale feature weighting as described above.
According to yet another aspect of the present application, there is provided a computer readable medium having stored thereon computer program instructions which, when executed by a processor, cause the processor to perform the intelligent particle size detection method using multi-scale feature weighting as described above.
Compared with the prior art, the intelligent particle size detection method using multi-scale feature weighting, the intelligent particle size detection system using multi-scale feature weighting and the electronic device provided by the application extract high-dimensional features in a pulverized coal image through machine vision based on deep learning and classify based on the extracted features to detect whether large-particle pulverized coal exceeding a predetermined size exists in pulverized coal to enter a combustion chamber, so that combustion efficiency is ensured. In particular, in the classification process, the detection method does not need to actually detect the object exceeding the preset size from the feature map, so that the detection precision can be improved by directly converting the overall scale of the feature map so as to obtain a fusion feature map sensitive to the scale and further obtaining a classifier sensitive to the scale through information of different scales.
Drawings
The above and other objects, features and advantages of the present application will become more apparent by describing in more detail embodiments of the present application with reference to the attached drawings. The accompanying drawings are included to provide a further understanding of the embodiments of the application and are incorporated in and constitute a part of this specification, illustrate embodiments of the application and together with the description serve to explain the principles of the application. In the drawings, like reference numbers generally represent like parts or steps.
FIG. 1 illustrates an application scenario of a smart particle size detection method using multi-scale feature weighting according to an embodiment of the present application;
FIG. 2 illustrates a flow diagram of a method of intelligent particle size detection using multi-scale feature weighting according to an embodiment of the present application;
FIG. 3 illustrates a system architecture diagram of a smart particle size detection method using multi-scale feature weighting according to an embodiment of the present application;
fig. 4 illustrates a flowchart of calculating a first distance, a second distance, and a third distance between the reference feature map and the first feature map, the second feature map, and the third feature map, respectively, in a smart particle size detection method using multi-scale feature weighting according to an embodiment of the present application;
FIG. 5 is a flow chart illustrating the process of passing the fused feature map through a classifier to obtain a classification result in a smart particle size detection method using multi-scale feature weighting according to an embodiment of the present application;
FIG. 6 illustrates a block diagram of a smart particle size detection system using multi-scale feature weighting according to an embodiment of the present application;
FIG. 7 illustrates a block diagram of a distance calculation unit in an intelligent particle size detection system using multi-scale feature weighting according to an embodiment of the present application;
FIG. 8 illustrates a block diagram of a classification result generation unit in an intelligent particle size detection system using multi-scale feature weighting according to an embodiment of the present application;
FIG. 9 illustrates a block diagram of an electronic device in accordance with an embodiment of the present application.
Detailed Description
Hereinafter, example embodiments according to the present application will be described in detail with reference to the accompanying drawings. It should be understood that the described embodiments are only some embodiments of the present application and not all embodiments of the present application, and that the present application is not limited by the example embodiments described herein.
Overview of a scene
As mentioned above, in the operation process of the pulverized coal furnace, pulverized coal pulverized into particles is blown to the combustion chamber, so that the pulverized coal is burnt out in the air. Therefore, the diameter of the pulverized coal particles needs to be sized to be sufficiently in contact with oxygen in a short time, however, in actual use, large-sized pulverized coal still enters the combustion chamber, which affects the combustion rate of the pulverized coal.
Therefore, the inventors of the present application have expected to detect whether large-particle pulverized coal exceeding a predetermined size exists in pulverized coal to be introduced into a combustion chamber through computer vision techniques based on deep learning, thereby securing a combustion rate of the pulverized coal.
The inventor of the present application finds that, in the technical solution of the present application, classification is mainly performed through features extracted by a convolutional neural network, that is, whether a feature map can belong to a class containing an object exceeding a predetermined size is determined through classification, and it is not necessary to actually detect an object exceeding the predetermined size from the feature map, so that a fused feature map sensitive to scale can be obtained directly based on transformation of the overall scale of the feature map, and further a classifier sensitive to scale can be obtained through information of different scales.
In addition, when fusing feature maps of different scales, the scheme of the application adopts a priori probability value based on similarity as weight, wherein the similarity is represented by using the distance between the feature map and a reference feature map, so that the contribution of the feature maps of different scales in the fused feature map can be determined based on the priori probability value of the similarity between the feature maps of different scales and the reference feature map, and the classification accuracy is improved.
Specifically, in the technical solution of the present application, after obtaining the coal dust image to enter the combustion chamber, the first feature map is obtained through a first convolutional neural network, and then the first feature map is downsampled and passed through a second convolutional neural network to obtain a second feature map, where the second convolutional neural network is to compensate for the loss of information caused by downsampling, and is preferably a convolutional neural network with a not large number of layers. Then, the second feature map is further down-sampled and passed through a third convolutional neural network to obtain a third feature map, and at the same time, the reference image of the large granular coal dust labeled to exceed the predetermined size is passed through the first convolutional neural network to obtain a reference feature map.
Next, after the reference feature maps are respectively converted to have the same scale as the first feature map, the second feature map and the third feature map, a first distance, a second distance and a third distance therebetween are respectively calculated, corresponding prior probability values p [2 x exp (-D) ]/[1+ exp (-D) ] are calculated, the first feature map, the second feature map and the third feature map are weighted by taking the values as weights to obtain a fused feature map, and the fused feature map is passed through a classifier to obtain a classification result, wherein the classification result is used for indicating whether large-particle coal dust with the size exceeding a predetermined size exists in coal dust to enter a combustion chamber.
Based on this, the present application proposes an intelligent particle size detection method using multi-scale feature weighting, which includes: acquiring an image to be detected, wherein the image to be detected is a pulverized coal image entering a combustion chamber; the image to be detected passes through a first convolutional neural network to extract a first characteristic diagram corresponding to the image to be detected; downsampling the first feature map to obtain a first downsampled feature map, and passing the first downsampled feature map through a second convolutional neural network to obtain a second feature map; downsampling the second feature map to obtain a second downsampled feature map, and passing the second downsampled feature map through a third convolutional neural network to obtain a third feature map; inputting the obtained reference image into the first convolution neural network to extract a reference characteristic diagram corresponding to the reference image, wherein the reference image is a coal powder image marked with large-particle coal powder with a size exceeding a preset size; respectively calculating a first distance, a second distance and a third distance between the reference feature map and the first feature map, the second feature map and the third feature map; calculating a first weight, a second weight, and a third weight respectively corresponding to the first distance, the second distance, and the third distance with a prior probability calculation formula as follows: p ═ 2 x exp (-D) ]/[1+ exp (-D) ], where p denotes the prior probability and D denotes the distance; fusing the first feature map, the second feature map and the third feature map by the first weight, the second weight and the third weight to obtain a fused feature map; and enabling the fusion characteristic diagram to pass through a classifier to obtain a classification result, wherein the classification result is used for indicating whether large-particle coal dust with the size exceeding the preset size exists in the coal dust to enter the combustion chamber in the image to be detected.
Fig. 1 illustrates an application scenario of a smart particle size detection method using multi-scale feature weighting according to an embodiment of the present application.
As shown in fig. 1, in the application scenario, an image to be detected is obtained through a camera (for example, as indicated by C in fig. 1), where the image to be detected is a coal powder image entering a combustion chamber; then, inputting the image to be detected into a server (for example, S shown in fig. 1) deployed with an intelligent particle size detection algorithm using multi-scale feature weighting, where the server can process the image to be detected using the intelligent particle size detection algorithm using multi-scale feature weighting to obtain a classification result, where the classification result is used to indicate whether large-particle pulverized coal exceeding a predetermined size exists in pulverized coal to enter a combustion chamber in the image to be detected.
Having described the general principles of the present application, various non-limiting embodiments of the present application will now be described with reference to the accompanying drawings.
Exemplary method
Fig. 2 illustrates a flow chart of a smart particle size detection method using multi-scale feature weighting. As shown in fig. 2, the intelligent particle size detection method using multi-scale feature weighting according to the embodiment of the present application includes: s110, acquiring an image to be detected, wherein the image to be detected is a pulverized coal image entering a combustion chamber; s120, enabling the image to be detected to pass through a first convolutional neural network so as to extract a first characteristic diagram corresponding to the image to be detected; s130, down-sampling the first characteristic diagram to obtain a first down-sampling characteristic diagram, and passing the first down-sampling characteristic diagram through a second convolutional neural network to obtain a second characteristic diagram; s140, down-sampling the second feature map to obtain a second down-sampled feature map, and passing the second down-sampled feature map through a third convolutional neural network to obtain a third feature map; s150, inputting the obtained reference image into the first convolution neural network to extract a reference characteristic diagram corresponding to the reference image, wherein the reference image is a coal powder image marked with large-particle coal powder with a size larger than a preset size; s160, respectively calculating a first distance, a second distance and a third distance between the reference feature map and the first feature map, the second feature map and the third feature map; s170, calculating a first weight, a second weight, and a third weight respectively corresponding to the first distance, the second distance, and the third distance according to the following prior probability calculation formula: p ═ 2 x exp (-D) ]/[1+ exp (-D) ], where p denotes the prior probability and D denotes the distance; s180, fusing the first feature map, the second feature map and the third feature map by the first weight, the second weight and the third weight to obtain a fused feature map; and S190, enabling the fusion characteristic diagram to pass through a classifier to obtain a classification result, wherein the classification result is used for indicating whether large-particle coal dust with the size exceeding the preset size exists in the coal dust to enter the combustion chamber in the image to be detected.
Fig. 3 illustrates an architectural diagram of a smart particle size detection method using multi-scale feature weighting according to an embodiment of the application. As shown IN fig. 3, IN the network architecture of the intelligent particle size detection method using multi-scale feature weighting, first, an image to be detected (e.g., IN1 as illustrated IN fig. 3) acquired by a camera is input into a first convolutional neural network (e.g., CNN1 as illustrated IN fig. 3) to obtain a first feature map (e.g., F1 as illustrated IN fig. 3); then, downsampling the first feature map to obtain a first downsampled feature map, and passing the first downsampled feature map through a second convolutional neural network (e.g., CNN2 as illustrated in fig. 3) to obtain a second feature map (e.g., F2 as illustrated in fig. 3); then, downsampling the second feature map to obtain a second downsampled feature map, and passing the second downsampled feature map through a third convolutional neural network (e.g., CNN3 as illustrated in fig. 3) to obtain a third feature map (e.g., F3 as illustrated in fig. 3); then, inputting the acquired reference image (e.g., P1 as illustrated in fig. 3) into the first convolutional neural network to extract a reference feature map (e.g., Fr as illustrated in fig. 3) corresponding to the reference image; then, calculating a first distance (e.g., D1 as illustrated in fig. 3), a second distance (e.g., D2 as illustrated in fig. 3), and a third distance (e.g., D3 as illustrated in fig. 3) between the reference feature map and the first, second, and third feature maps, respectively; then, calculating a first weight, a second weight and a third weight corresponding to the first distance, the second distance and the third distance, respectively; then, fusing the first feature map, the second feature map and the third feature map with the first weight, the second weight and the third weight to obtain a fused feature map (e.g., Fc as illustrated in fig. 3); then, the fused feature map is passed through a classifier (e.g., a classifier as illustrated in fig. 3) to obtain a classification result, which is used to indicate whether large-particle coal dust exceeding a predetermined size exists in the coal dust to enter the combustion chamber in the image to be detected.
In step S110, an image to be detected, which is an image of pulverized coal entering the combustion chamber, is acquired. Specifically, in this application embodiment, the camera can be used to obtain the coal dust image to be entered into the combustion chamber, that is, in this application scheme, the computer vision technology is used to further detect the coal dust image to be entered into the combustion chamber on the visual level.
In step S120, the image to be detected is passed through a first convolutional neural network to extract a first feature map corresponding to the image to be detected. Namely, a first convolution neural network is adopted to extract high-dimensional features in the image to be detected.
It will be appreciated by those of ordinary skill in the art that the convolutional neural network has excellent performance in extracting local spatial features, and in particular, in the embodiments of the present application, the first convolutional neural network is implemented as a deep residual neural network, e.g., ResNet 50. It should be known to those skilled in the art that, compared to the conventional convolutional neural network, the deep residual network is an optimized network structure proposed on the basis of the conventional convolutional neural network, which mainly solves the problem of gradient disappearance during the training process. The depth residual error network introduces a residual error network structure, the network layer can be made deeper through the residual error network structure, and the problem of gradient disappearance can not occur. The residual error network uses the cross-layer link thought of a high-speed network for reference, breaks through the convention that the traditional neural network only can provide N layers as input from the input layer of the N-1 layer, enables the output of a certain layer to directly cross several layers as the input of the later layer, and has the significance of providing a new direction for the difficult problem that the error rate of the whole learning model is not reduced and inversely increased by superposing multiple layers of networks.
In step S130, the first feature map is downsampled to obtain a first downsampled feature map, and the first downsampled feature map is passed through a second convolutional neural network to obtain a second feature map. That is, the first feature map is downsampled to reduce the size of the first feature map to obtain a first downsampled feature map, and then a second convolutional neural network is used to extract higher-dimensional features of the first downsampled feature map.
Specifically, in the embodiment of the present application, the second convolutional neural network has a preset depth, and the preset depth is greater than or equal to 5 and less than or equal to 10. It should be understood that the second convolutional neural network is to compensate for the loss of information due to the downsampling, and those skilled in the art will appreciate that the higher the depth of the convolutional neural network, the more abstract the extracted features, and the more focused the details, in this application, the more focused the shape features of the image, and therefore, preferably 5 to 10 layers of convolutional neural network. In particular, in the present embodiment, the second convolutional neural network is implemented as a deep residual neural network, e.g., ResNet 50.
In step S140, the second feature map is downsampled to obtain a second downsampled feature map, and the second downsampled feature map is passed through a third convolutional neural network to obtain a third feature map. That is, the second feature map is downsampled to reduce the size of the second feature map to obtain a second downsampled feature map, and then a third convolutional neural network is used to extract higher-dimensional features of the second downsampled feature map. It should be understood that the third convolutional neural network is to compensate for the information loss caused by downsampling the second feature map, and preferably, the third convolutional neural network is a convolutional neural network with a small number of layers. In particular, in the present embodiment, the third convolutional neural network is implemented as a deep residual neural network, e.g., ResNet 50.
In step S150, the obtained reference image is input into the first convolutional neural network to extract a reference feature map corresponding to the reference image, where the reference image is a coal powder image marked with large-particle coal powder exceeding a predetermined size. That is, the first convolutional neural network is used to extract high-dimensional features in the reference image.
In step S160, a first distance, a second distance, and a third distance between the reference feature map and the first feature map, the second feature map, and the third feature map are calculated, respectively. It should be appreciated that the distances may represent feature difference information between the respective feature maps.
Specifically, in the embodiment of the present application, the process of calculating the first distance, the second distance, and the third distance between the reference feature map and the first feature map, the second feature map, and the third feature map respectively includes: and respectively calculating cosine distances among the reference feature map, the first feature map, the second feature map and the third feature map to obtain the first distance, the second distance and the third distance. One of ordinary skill in the art will appreciate that the cosine distance may analyze the similarity between two signatures, which represents the relative difference in the direction of the values.
It should be noted that in other examples of the present application, the first distance, the second distance, and the third distance between the reference feature map and the first feature map, the second feature map, and the third feature map may also be calculated in other manners. For example, in another example of the present application, the process of calculating the first distance, the second distance, and the third distance between the reference feature map and the first feature map, the second feature map, and the third feature map, respectively, includes: and respectively calculating the mean square deviations between the reference feature map and the first feature map, the second feature map and the third feature map to obtain the first distance, the second distance and the third distance. It will be appreciated by those skilled in the art that the mean square error, also known as the standard deviation, is the arithmetic square root of the variance, expressed as σ, and is most commonly used in probability statistics as a measure of the degree of statistical distribution, which reflects the degree of dispersion of a data set. It should be understood that, in the present application, the mean square error between the reference feature map and the first, second and third feature maps is calculated to obtain the first, second and third distances, which can reflect the difference in feature distribution between the respective two feature maps.
In particular, in the embodiment of the present application, the process of calculating the first distance, the second distance, and the third distance between the reference feature map and the first feature map, the second feature map, and the third feature map, respectively, further includes: firstly, unifying the scale between the reference feature map and the first feature map, and calculating a first distance between the reference feature map and the scale-adjusted first feature map. Then, unifying the scale between the reference feature map and the second feature map, and calculating a second distance between the reference feature map and the second feature map after the scale adjustment. Then, unifying the scale between the reference feature map and the third feature map, and calculating a third distance between the reference feature map and the scaled third feature map. That is, before the distances are calculated separately, the scale unification is performed. Specifically, the method can be implemented by means of upsampling, or downsampling, and the like.
Fig. 4 illustrates a flowchart of calculating a first distance, a second distance, and a third distance between the reference feature map and the first feature map, the second feature map, and the third feature map, respectively, in an intelligent particle size detection method using multi-scale feature weighting according to an embodiment of the present application. As shown in fig. 4, in the embodiment of the present application, calculating a first distance, a second distance, and a third distance between the reference feature map and the first feature map, the second feature map, and the third feature map respectively includes: s210, unifying the scale between the reference feature map and the first feature map; s220, unifying the scale between the reference feature map and the second feature map; and S230, unifying the scale between the reference feature map and the third feature map.
In step S170, a first weight, a second weight, and a third weight corresponding to the first distance, the second distance, and the third distance, respectively, are calculated by the following prior probability calculation formula: p ═ 2 × exp (-D) ]/[1+ exp (-D) ], where p denotes the prior probability and D denotes the distance. That is, the first weight, the second weight, and the third weight are determined by prior probabilities calculated based on the first distance, the second distance, and the third distance, respectively.
In step S180, the first feature map, the second feature map, and the third feature map are fused by the first weight, the second weight, and the third weight to obtain a fused feature map. That is, the feature maps are weighted by using the first weight, the second weight, and the third weight as weighting coefficients of the first feature map, the second feature map, and the third feature map, respectively, and are fused by pixel position to obtain a fused feature map.
In step S190, the fusion feature map is passed through a classifier to obtain a classification result, where the classification result is used to indicate whether there is large-particle coal dust exceeding a predetermined size in the coal dust to enter the combustion chamber in the image to be detected. That is, in a decoupling manner, the classifier includes an encoder, and the encoder may be composed of a convolutional layer, a pooling layer, or a fully-connected layer.
Specifically, in the embodiment of the present application, the process of passing the fused feature map through a classifier to obtain a classification result includes: firstly, the fused feature map is passed through one or more fully-connected layers to obtain a classified feature vector, that is, the one or more fully-connected layers are used as encoders to encode the fused feature map so as to fully utilize the information of each position in the fused feature map to obtain the classified feature vector. Then, the classification feature vector is input into a Softmax classification function to obtain the classification result.
Fig. 5 illustrates a flowchart of passing the fused feature map through a classifier to obtain a classification result in an intelligent particle size detection method using multi-scale feature weighting according to an embodiment of the present application. As shown in fig. 5, in the embodiment of the present application, passing the fused feature map through a classifier to obtain a classification result includes: s210, passing the fusion feature map through one or more full connection layers to obtain a classification feature vector; and S220, inputting the classification feature vector into a Softmax classification function to obtain the classification result.
In summary, the intelligent particle size detection method using multi-scale feature weighting according to the embodiment of the present application is elucidated, which detects whether large-particle pulverized coal exceeding a predetermined size exists in pulverized coal to be introduced into a combustion chamber by extracting high-dimensional features in a pulverized coal image based on machine vision of deep learning and classifying based on the extracted features, so as to ensure combustion efficiency. In particular, in the classification process, the detection method does not need to actually detect the object exceeding the preset size from the feature map, so that the detection precision can be improved by directly converting the overall scale of the feature map so as to obtain a fusion feature map sensitive to the scale and further obtaining a classifier sensitive to the scale through information of different scales.
Exemplary System
FIG. 6 illustrates a block diagram of a smart particle size detection system using multi-scale feature weighting according to an embodiment of the present application.
As shown in fig. 6, an intelligent particle size detection system 600 using multi-scale feature weighting according to an embodiment of the present application includes: the image acquiring unit 610 to be detected is used for acquiring an image to be detected, wherein the image to be detected is a coal powder image entering a combustion chamber; a first feature map generating unit 620, configured to extract a first feature map corresponding to the image to be detected by passing the image to be detected obtained by the image to be detected obtaining unit through a first convolutional neural network; a second feature map generating unit 630, configured to down-sample the first feature map obtained by the first feature map generating unit 620 to obtain a first down-sampled feature map, and pass the first down-sampled feature map through a second convolutional neural network to obtain a second feature map; a third feature map generation unit 640, configured to down-sample the second feature map obtained by the second feature map generation unit 630 to obtain a second down-sampled feature map, and pass the second down-sampled feature map through a third convolutional neural network to obtain a third feature map; a reference feature map generating unit 650 configured to input the acquired reference image into the first convolutional neural network to extract a reference feature map corresponding to the reference image, where the reference image is a pulverized coal image marked with large-particle pulverized coal exceeding a predetermined size; a distance calculating unit 660, configured to calculate a first distance, a second distance, and a third distance between the reference feature map obtained by the reference feature map generating unit 650 and the first feature map obtained by the first feature map generating unit 620, the second feature map obtained by the second feature map generating unit 630, and the third feature map obtained by the third feature map generating unit 640, respectively; a weight calculation unit 670, configured to calculate a first weight, a second weight, and a third weight respectively corresponding to the first distance, the second distance, and the third distance obtained by the distance calculation unit 660, according to the following prior probability calculation formula: p ═ 2 x exp (-D) ]/[1+ exp (-D) ], where p denotes the prior probability and D denotes the distance; a fused feature map generating unit 680, configured to fuse the first feature map obtained by the first feature map generating unit 620, the second feature map obtained by the second feature map generating unit 630, and the third feature map obtained by the third feature map generating unit 640, with the first weight, the second weight, and the third weight obtained by the weight calculating unit 670, to obtain a fused feature map; and a classification result generating unit 690, configured to pass the fusion feature map obtained by the fusion feature map generating unit 680 through a classifier to obtain a classification result, where the classification result is used to indicate whether large-particle coal dust exceeding a predetermined size exists in coal dust to enter a combustion chamber in the image to be detected.
In one example, in the above-described intelligent detection system 600, the second convolutional neural network has a preset depth, and the preset depth is greater than or equal to 5 and less than or equal to 10.
In an example, in the above intelligent detection system 600, the distance calculation unit 660 is further configured to: and respectively calculating cosine distances among the reference feature map, the first feature map, the second feature map and the third feature map to obtain the first distance, the second distance and the third distance.
In an example, in the above intelligent detection system 600, the distance calculation unit 660 is further configured to: and respectively calculating the mean square deviations between the reference feature map and the first feature map, the second feature map and the third feature map to obtain the first distance, the second distance and the third distance.
In one example, in the above-mentioned smart detection system 600, as shown in fig. 7, the distance calculation unit 660 includes: a first scale unifying subunit 661, configured to unify the scale between the reference feature map and the first feature map; a second scale unifying subunit 662 configured to unify the scale between the reference feature map and the second feature map; and a third scale unifying subunit 663, configured to unify the scale between the reference feature map and the third feature map.
In an example, in the above-mentioned smart detection system 600, as shown in fig. 8, the classification result generating unit 690 includes: a classification feature vector generation subunit 691, configured to pass the fused feature map through one or more fully connected layers to obtain a classification feature vector; and a classification subunit 692, configured to input the classification feature vector obtained by the classification feature vector generation subunit 691 into a Softmax classification function, so as to obtain the classification result.
In one example, in the above-described intelligent detection system 600, the first convolutional neural network, the second convolutional neural network, and the third convolutional neural network are deep residual error networks.
Here, it will be understood by those skilled in the art that the specific functions and operations of the respective units and modules in the above-described smart detection system 600 have been described in detail in the above description of the smart particle size detection method using multi-scale feature weighting with reference to fig. 1 to 5, and thus, a repetitive description thereof will be omitted.
As described above, the intelligent detection system 600 according to the embodiment of the present application can be implemented in various terminal devices, such as a server for intelligent detection of large-particle coal dust. In one example, the smart detection system 600 according to the embodiment of the present application may be integrated into a terminal device as a software module and/or a hardware module. For example, the smart detection system 600 may be a software module in the operating system of the terminal device, or may be an application developed for the terminal device; of course, the smart detection system 600 may also be one of many hardware modules of the terminal device.
Alternatively, in another example, the smart detection system 600 and the terminal device may be separate devices, and the smart detection system 600 may be connected to the terminal device through a wired and/or wireless network and transmit the interaction information according to an agreed data format.
Exemplary electronic device
Next, an electronic apparatus according to an embodiment of the present application is described with reference to fig. 9.
FIG. 9 illustrates a block diagram of an electronic device in accordance with an embodiment of the present application.
As shown in fig. 9, the electronic device 10 includes one or more processors 11 and a memory 12.
The processor 11 may be a Central Processing Unit (CPU) or other form of processing unit having data processing capabilities and/or instruction execution capabilities, and may control other components in the electronic device 10 to perform desired functions.
In one example, the electronic device 10 may further include: an input system 13 and an output system 14, which are interconnected by a bus system and/or other form of connection mechanism (not shown).
The input system 13 may comprise, for example, a keyboard, a mouse, etc.
The output system 14 may output various information including classification results and the like to the outside. The output system 14 may include, for example, a display, speakers, a printer, and a communication network and its connected remote output devices, among others.
Of course, for simplicity, only some of the components of the electronic device 10 relevant to the present application are shown in fig. 9, and components such as buses, input/output interfaces, and the like are omitted. In addition, the electronic device 10 may include any other suitable components depending on the particular application.
Exemplary computer program product and computer-readable storage Medium
In addition to the above-described methods and apparatus, embodiments of the present application may also be a computer program product comprising computer program instructions that, when executed by a processor, cause the processor to perform the steps in the functions in the intelligent particle size detection method using multi-scale feature weighting according to various embodiments of the present application described in the "exemplary methods" section above of this specification.
The computer program product may be written with program code for performing the operations of embodiments of the present application in any combination of one or more programming languages, including an object oriented programming language such as Java, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computing device, partly on the user's device, as a stand-alone software package, partly on the user's computing device and partly on a remote computing device, or entirely on the remote computing device or server.
Furthermore, embodiments of the present application may also be a computer-readable storage medium having stored thereon computer program instructions that, when executed by a processor, cause the processor to perform the steps in the intelligent particle size detection method using multi-scale feature weighting described in the "exemplary methods" section above in this specification.
The computer-readable storage medium may take any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may include, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, or device, or any combination of the foregoing. More specific examples (a non-exhaustive list) of the readable storage medium include: an electrical connection having one or more wires, a portable disk, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
Claims (10)
1. A method for intelligent particle size detection using multi-scale feature weighting, comprising:
acquiring an image to be detected, wherein the image to be detected is a pulverized coal image entering a combustion chamber;
the image to be detected passes through a first convolutional neural network to extract a first characteristic diagram corresponding to the image to be detected;
downsampling the first feature map to obtain a first downsampled feature map, and passing the first downsampled feature map through a second convolutional neural network to obtain a second feature map;
downsampling the second feature map to obtain a second downsampled feature map, and passing the second downsampled feature map through a third convolutional neural network to obtain a third feature map;
inputting the obtained reference image into the first convolution neural network to extract a reference characteristic diagram corresponding to the reference image, wherein the reference image is a coal powder image marked with large-particle coal powder with a size exceeding a preset size;
respectively calculating a first distance, a second distance and a third distance between the reference feature map and the first feature map, the second feature map and the third feature map;
calculating a first weight, a second weight, and a third weight respectively corresponding to the first distance, the second distance, and the third distance with a prior probability calculation formula as follows: p ═ 2 x exp (-D) ]/[1+ exp (-D) ], where p denotes the prior probability and D denotes the distance;
fusing the first feature map, the second feature map and the third feature map by the first weight, the second weight and the third weight to obtain a fused feature map; and
and passing the fusion characteristic diagram through a classifier to obtain a classification result, wherein the classification result is used for indicating whether large-particle coal dust with a size exceeding a preset size exists in the coal dust to enter a combustion chamber in the image to be detected.
2. The smart particle size detection method using multi-scale feature weighting according to claim 1, wherein the second convolutional neural network has a preset depth, and the preset depth is greater than or equal to 5 and less than or equal to 10.
3. The intelligent particle size detection method using multi-scale feature weighting as recited in claim 1, wherein calculating first, second, and third distances between the reference feature map and the first, second, and third feature maps, respectively, comprises:
and respectively calculating cosine distances among the reference feature map, the first feature map, the second feature map and the third feature map to obtain the first distance, the second distance and the third distance.
4. The intelligent particle size detection method using multi-scale feature weighting of claim 2, wherein calculating a first distance, a second distance, and a third distance between the reference feature map and the first feature map, the second feature map, and the third feature map, respectively, comprises:
and respectively calculating the mean square deviations between the reference feature map and the first feature map, the second feature map and the third feature map to obtain the first distance, the second distance and the third distance.
5. The intelligent particle size detection method using multi-scale feature weighting according to claim 3 or 4, wherein calculating a first distance, a second distance and a third distance between the reference feature map and the first feature map, the second feature map and the third feature map respectively comprises:
unifying a scale between the reference feature map and the first feature map;
unifying the scale between the reference feature map and the second feature map; and
unifying the scale between the reference feature map and the third feature map.
6. The intelligent particle size detection method using multi-scale feature weighting according to claim 1, wherein passing the fused feature map through a classifier to obtain a classification result comprises:
passing the fused feature map through one or more fully connected layers to obtain a classified feature vector; and
inputting the classification feature vector into a Softmax classification function to obtain the classification result.
7. The smart particle size detection method using multi-scale feature weighting as recited in claim 2, wherein the first convolutional neural network, the second convolutional neural network, and the third convolutional neural network are deep residual networks.
8. A smart particle size detection system using multi-scale feature weighting, comprising:
the device comprises an image acquisition unit to be detected, a data acquisition unit and a data processing unit, wherein the image acquisition unit to be detected is used for acquiring an image to be detected, and the image to be detected is a pulverized coal image entering a combustion chamber;
the first characteristic diagram generating unit is used for enabling the image to be detected obtained by the image to be detected obtaining unit to pass through a first convolutional neural network so as to extract a first characteristic diagram corresponding to the image to be detected;
a second feature map generation unit, configured to down-sample the first feature map obtained by the first feature map generation unit to obtain a first down-sampled feature map, and pass the first down-sampled feature map through a second convolutional neural network to obtain a second feature map;
a third feature map generation unit configured to down-sample the second feature map obtained by the second feature map generation unit to obtain a second down-sampled feature map, and pass the second down-sampled feature map through a third convolutional neural network to obtain a third feature map;
a reference feature map generating unit, configured to input the obtained reference image into the first convolutional neural network to extract a reference feature map corresponding to the reference image, where the reference image is a pulverized coal image marked with large-particle pulverized coal exceeding a predetermined size;
a distance calculating unit configured to calculate a first distance, a second distance, and a third distance between the reference feature map obtained by the reference feature map generating unit and the first feature map obtained by the first feature map generating unit, the second feature map obtained by the second feature map generating unit, and the third feature map obtained by the third feature map generating unit, respectively;
a weight calculation unit configured to calculate a first weight, a second weight, and a third weight respectively corresponding to the first distance, the second distance, and the third distance obtained by the distance calculation unit, using a prior probability calculation formula as follows: p ═ 2 x exp (-D) ]/[1+ exp (-D) ], where p denotes the prior probability and D denotes the distance;
a fused feature map generating unit configured to fuse the first feature map obtained by the first feature map generating unit, the second feature map obtained by the second feature map generating unit, and the third feature map obtained by the third feature map generating unit with the first weight, the second weight, and the third weight obtained by the weight calculating unit to obtain a fused feature map; and
and the classification result generating unit is used for enabling the fusion characteristic diagram obtained by the fusion characteristic diagram generating unit to pass through a classifier so as to obtain a classification result, and the classification result is used for indicating whether large-particle coal dust with the size exceeding the preset size exists in the coal dust to enter the combustion chamber in the image to be detected.
9. The smart particle size detection system using multi-scale feature weighting as recited in claim 8, wherein the distance calculation unit comprises:
a first scale unifying subunit configured to unify a scale between the reference feature map and the first feature map;
a second scale unifying subunit, configured to unify a scale between the reference feature map and the second feature map; and
and the third dimension unifying subunit is used for unifying the dimension between the reference feature map and the third feature map.
10. An electronic device, comprising:
a processor; and
a memory having stored therein computer program instructions which, when executed by the processor, cause the processor to perform the intelligent particle size detection method using multi-scale feature weighting of any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110155232.4A CN112800995A (en) | 2021-02-04 | 2021-02-04 | Intelligent particle size detection method using multi-scale feature weighting |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110155232.4A CN112800995A (en) | 2021-02-04 | 2021-02-04 | Intelligent particle size detection method using multi-scale feature weighting |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112800995A true CN112800995A (en) | 2021-05-14 |
Family
ID=75814219
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110155232.4A Pending CN112800995A (en) | 2021-02-04 | 2021-02-04 | Intelligent particle size detection method using multi-scale feature weighting |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112800995A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115818166A (en) * | 2022-11-15 | 2023-03-21 | 华能伊敏煤电有限责任公司 | Unattended automatic control method and system for wheel hopper continuous system |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2005208024A (en) * | 2003-12-26 | 2005-08-04 | Jfe Steel Kk | Method for forming grain size distribution of powdery/granular material |
| CN104634706A (en) * | 2015-01-23 | 2015-05-20 | 国家电网公司 | Neural network-based soft measurement method for pulverized coal fineness |
| CN111488777A (en) * | 2019-01-28 | 2020-08-04 | 北京地平线机器人技术研发有限公司 | Object identification method, object identification device and electronic equipment |
| CN112001253A (en) * | 2020-07-23 | 2020-11-27 | 西安科技大学 | Coal dust particle image identification method based on improved Fast R-CNN |
| CN112084865A (en) * | 2020-08-06 | 2020-12-15 | 中国科学院空天信息创新研究院 | Target detection method, target detection device, electronic equipment and storage medium |
-
2021
- 2021-02-04 CN CN202110155232.4A patent/CN112800995A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2005208024A (en) * | 2003-12-26 | 2005-08-04 | Jfe Steel Kk | Method for forming grain size distribution of powdery/granular material |
| CN104634706A (en) * | 2015-01-23 | 2015-05-20 | 国家电网公司 | Neural network-based soft measurement method for pulverized coal fineness |
| CN111488777A (en) * | 2019-01-28 | 2020-08-04 | 北京地平线机器人技术研发有限公司 | Object identification method, object identification device and electronic equipment |
| CN112001253A (en) * | 2020-07-23 | 2020-11-27 | 西安科技大学 | Coal dust particle image identification method based on improved Fast R-CNN |
| CN112084865A (en) * | 2020-08-06 | 2020-12-15 | 中国科学院空天信息创新研究院 | Target detection method, target detection device, electronic equipment and storage medium |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115818166A (en) * | 2022-11-15 | 2023-03-21 | 华能伊敏煤电有限责任公司 | Unattended automatic control method and system for wheel hopper continuous system |
| CN115818166B (en) * | 2022-11-15 | 2023-09-26 | 华能伊敏煤电有限责任公司 | Unmanned automatic control method and system for continuous system of wheel bucket |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Wang et al. | Automatic fault diagnosis of infrared insulator images based on image instance segmentation and temperature analysis | |
| CN115761642A (en) | Image processing-based crushing operation monitoring method and system | |
| CN116639010A (en) | Intelligent control system and method for charging pile | |
| CN116247824B (en) | Control method and system for power equipment | |
| CN115620303B (en) | Personnel file intelligent management system | |
| CN115783923A (en) | Elevator fault mode identification system based on big data | |
| CN116245513B (en) | Automatic operation and maintenance system and method based on rule base | |
| CN115456789B (en) | Abnormal transaction detection method and system based on transaction pattern recognition | |
| CN115471216B (en) | Data management method of intelligent laboratory management platform | |
| CN115859437A (en) | Jacket underwater stress detection system based on distributed optical fiber sensing system | |
| CN114580515A (en) | Neural network training method for intelligent detection of semiconductor desoldering | |
| CN116343301B (en) | Personnel information intelligent verification system based on face recognition | |
| CN117077075A (en) | Water quality monitoring system and method for environmental protection | |
| CN116309580A (en) | Oil and gas pipeline corrosion detection method based on magnetic stress | |
| CN117269644A (en) | Line fault monitoring system and method for current transformer | |
| CN112733785A (en) | Stability detection method of information equipment based on layer depth and receptive field | |
| CN115146676A (en) | Circuit fault detection method and system | |
| CN112800995A (en) | Intelligent particle size detection method using multi-scale feature weighting | |
| CN112960213A (en) | Intelligent package quality detection method using characteristic probability distribution representation | |
| CN117495421A (en) | Power grid communication engineering cost prediction method based on power communication network construction | |
| CN117225091A (en) | System and method for monitoring running state of bag-type dust collector | |
| CN117274689A (en) | Detection method and system for detecting defects of packaging box | |
| CN116797586A (en) | Automatic paper cup defect detection method and system | |
| CN115510900A (en) | Automatic circuit fault diagnosis method and system | |
| CN115331081A (en) | Image target detection method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20210514 |